Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00020
Ondřej Benedikt, Javier Pérez-Rodríguez, P. Yomsi, M. Sojka
Reducing heat dissipation is critical for modern multi-core systems to meet increasing computational performance requirements. In this paper, we investigate the impact of idle-time distribution on the peak temperature of Multi-processor System-on-Chip (MPSoCs) for the constrained-deadline non-preemptive task scheduling problem that is common in safety-critical systems. It is assumed that the transient thermal behavior of the platform cannot be neglected and must be modeled and accounted for by the optimization algorithms. In this context, we derive a dual-node thermal model that can be well applied to a dual-cluster i.MX8 QuadMax from NXP. Based on this model, we implement two offline optimization-based strategies, including an iterative per-core approach based on the principles presented in the related literature and a novel holistic approach. The results show that the per-core approach and the holistic approach reduce the peak temperature by 7.1% and 14% on average compared to the traditional non-thermal approach. We perform the experiments on the i.MX8 QuadMax platform to validate the applicability of the results and observe a good match between the model-based simulations and the actual physical platform measurements.
{"title":"Reducing Peak Temperature by Redistributing Idle-Time in Modern MPSoCs","authors":"Ondřej Benedikt, Javier Pérez-Rodríguez, P. Yomsi, M. Sojka","doi":"10.1109/ISORC58943.2023.00020","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00020","url":null,"abstract":"Reducing heat dissipation is critical for modern multi-core systems to meet increasing computational performance requirements. In this paper, we investigate the impact of idle-time distribution on the peak temperature of Multi-processor System-on-Chip (MPSoCs) for the constrained-deadline non-preemptive task scheduling problem that is common in safety-critical systems. It is assumed that the transient thermal behavior of the platform cannot be neglected and must be modeled and accounted for by the optimization algorithms. In this context, we derive a dual-node thermal model that can be well applied to a dual-cluster i.MX8 QuadMax from NXP. Based on this model, we implement two offline optimization-based strategies, including an iterative per-core approach based on the principles presented in the related literature and a novel holistic approach. The results show that the per-core approach and the holistic approach reduce the peak temperature by 7.1% and 14% on average compared to the traditional non-thermal approach. We perform the experiments on the i.MX8 QuadMax platform to validate the applicability of the results and observe a good match between the model-based simulations and the actual physical platform measurements.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122928806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00024
Maria J. P. Peixoto, Akramul Azim
This paper discusses the benefits of a distributed and collaborative approach for optimizing real-time intelligent systems with complex task scheduling requirements. We focus on the specific example of implementing car platoons in urban traffic, which requires efficient task mapping and scheduling to maximize efficiency and ensure optimal performance. To meet the demands of a car platoon environment, a collaborative task management system, EDFHC-ML, is proposed for connected autonomous vehicles using edge, fog, and cloud computing. We also evaluated our approach with three others and found that our method had the best performance in executing tasks within the deadline. Our proposed approach is beneficial for developing intelligent systems that require high-performance computing and real-time response.
{"title":"A collaborative and distributed task management system for real-time systems","authors":"Maria J. P. Peixoto, Akramul Azim","doi":"10.1109/ISORC58943.2023.00024","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00024","url":null,"abstract":"This paper discusses the benefits of a distributed and collaborative approach for optimizing real-time intelligent systems with complex task scheduling requirements. We focus on the specific example of implementing car platoons in urban traffic, which requires efficient task mapping and scheduling to maximize efficiency and ensure optimal performance. To meet the demands of a car platoon environment, a collaborative task management system, EDFHC-ML, is proposed for connected autonomous vehicles using edge, fog, and cloud computing. We also evaluated our approach with three others and found that our method had the best performance in executing tasks within the deadline. Our proposed approach is beneficial for developing intelligent systems that require high-performance computing and real-time response.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114563794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00018
Francis Akowuah, Kenneth Fletcher, Fanxin Kong
Cyber-physical systems (CPS) are susceptible to physical attacks, and researchers are exploring ways to detect them. One method involves monitoring the system for a set duration, known as the time-window, and identifying residual errors that exceed a predetermined threshold. However, this approach means that any sensor attack alert can only be triggered after the time-window has elapsed. The length of the time-window affects the detection delay and the likelihood of false alarms, with a shorter time-window leading to quicker detection but a higher false positive rate, and a longer time-window resulting in slower detection but a lower false positive rate.While researchers aim to choose a fixed time-window that balances a low false positive rate and short detection delay, this goal is difficult to attain due to a trade-off between the two. An alternative solution proposed in this paper is to have a variable time-window that can adapt based on the current state of the CPS. For instance, if the CPS is heading towards an unsafe state, it is more crucial to reduce the detection delay (by decreasing the time-window) rather than reducing the false alarm rate, and vice versa. The paper presents a sensor attack detection framework that dynamically adjusts the time-window, enabling attack alerts to be triggered before the system enters dangerous regions, ensuring timely detection. This framework consists of three components: attack detector, state predictor, and window adaptor. We have evaluated our work using real-world data, and the results demonstrate that our solution improves the usability and timeliness of time-window-based attack detectors.
{"title":"Variable Window and Deadline-Aware Sensor Attack Detector for Automotive CPS","authors":"Francis Akowuah, Kenneth Fletcher, Fanxin Kong","doi":"10.1109/ISORC58943.2023.00018","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00018","url":null,"abstract":"Cyber-physical systems (CPS) are susceptible to physical attacks, and researchers are exploring ways to detect them. One method involves monitoring the system for a set duration, known as the time-window, and identifying residual errors that exceed a predetermined threshold. However, this approach means that any sensor attack alert can only be triggered after the time-window has elapsed. The length of the time-window affects the detection delay and the likelihood of false alarms, with a shorter time-window leading to quicker detection but a higher false positive rate, and a longer time-window resulting in slower detection but a lower false positive rate.While researchers aim to choose a fixed time-window that balances a low false positive rate and short detection delay, this goal is difficult to attain due to a trade-off between the two. An alternative solution proposed in this paper is to have a variable time-window that can adapt based on the current state of the CPS. For instance, if the CPS is heading towards an unsafe state, it is more crucial to reduce the detection delay (by decreasing the time-window) rather than reducing the false alarm rate, and vice versa. The paper presents a sensor attack detection framework that dynamically adjusts the time-window, enabling attack alerts to be triggered before the system enters dangerous regions, ensuring timely detection. This framework consists of three components: attack detector, state predictor, and window adaptor. We have evaluated our work using real-world data, and the results demonstrate that our solution improves the usability and timeliness of time-window-based attack detectors.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132605168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00039
Ziran Min, Shuang Zhou, Zhuangwei Kang, Shashank Shekhar, C. Mahmoudi, A. Gokhale, A. Gokhale
Industry 4.0 is leading factories to undergo a significant transformation, where automation is achieved through the use of modern smart technologies, such as 5G & beyond $(5 mathrm{G}+)$ network and digital twins. Yet, many Industrial Internet of Things (IIoT) applications, including smart factories and robotic repair, present challenges in delivering dedicated and real-time network services between the physical world entities and their digital twins due to the different network requirements of each sub tasks of the applications. Although 5G+ networks can provide high-speed, low-latency, and reliable network services, managing and optimizing the network resources in real-time remains complex and time-consuming. To address these challenges, this paper proposes solutions to manage and optimize $5 mathrm{G}+$ network resources in real-time, and deliver dynamic and real time network requirements of multi-task digital twin applications.
{"title":"Managing and Optimizing 5G & Beyond Network Resources for Multi-Task Digital Twin Applications in Industry 4.0","authors":"Ziran Min, Shuang Zhou, Zhuangwei Kang, Shashank Shekhar, C. Mahmoudi, A. Gokhale, A. Gokhale","doi":"10.1109/ISORC58943.2023.00039","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00039","url":null,"abstract":"Industry 4.0 is leading factories to undergo a significant transformation, where automation is achieved through the use of modern smart technologies, such as 5G & beyond $(5 mathrm{G}+)$ network and digital twins. Yet, many Industrial Internet of Things (IIoT) applications, including smart factories and robotic repair, present challenges in delivering dedicated and real-time network services between the physical world entities and their digital twins due to the different network requirements of each sub tasks of the applications. Although 5G+ networks can provide high-speed, low-latency, and reliable network services, managing and optimizing the network resources in real-time remains complex and time-consuming. To address these challenges, this paper proposes solutions to manage and optimize $5 mathrm{G}+$ network resources in real-time, and deliver dynamic and real time network requirements of multi-task digital twin applications.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129627337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00031
Luca Abeni, Remo Andreoli, H. Gustafsson, R. Mini, T. Cucinotta
This paper presents the Fault-Tolerant Real-Time Cloud (FTRTC) project that aims to design cloud computing infrastructures capable of hosting highly reliable and real-time applications. These applications are characterized by strict timing and reliability constraints, as well as critical failure scenarios. For instance, such requirements are commonly found in the context of Industry 4.0. We present a formalization of the problem of designing real-time cloud applications supporting an adjustable level of fault tolerance throughout their distributed execution in a cloud infrastructure. The contributions presented in this paper indicate important research directions when building cloud infrastructures able to supporting ultra-reliable real-time applications.
{"title":"Fault Tolerance in Real-Time Cloud Computing","authors":"Luca Abeni, Remo Andreoli, H. Gustafsson, R. Mini, T. Cucinotta","doi":"10.1109/ISORC58943.2023.00031","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00031","url":null,"abstract":"This paper presents the Fault-Tolerant Real-Time Cloud (FTRTC) project that aims to design cloud computing infrastructures capable of hosting highly reliable and real-time applications. These applications are characterized by strict timing and reliability constraints, as well as critical failure scenarios. For instance, such requirements are commonly found in the context of Industry 4.0. We present a formalization of the problem of designing real-time cloud applications supporting an adjustable level of fault tolerance throughout their distributed execution in a cloud infrastructure. The contributions presented in this paper indicate important research directions when building cloud infrastructures able to supporting ultra-reliable real-time applications.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130138481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00029
M. A. D. Oliveira, G. H. Cavalheiro, Vinícius A. Cerbaro, C. Fraisse
Meteorological observations are widely used as input for disease alert systems in agriculture. In Florida, USA, the AgroClimate Advisory Systems provide disease alerts to growers of various crops, including strawberries, blueberries, and citrus. Data observed in weather stations belonging to FAWN (Florida Automated Weather Network) are used to simulate disease risk, and growers are notified when environmental conditions are favorable for infection, helping them decide when to spray for prevention. However, observation problems in weather stations, such as sensor or communication failures, can compromise the reliability of these applications, which unfortunately are common in this context. Thus, this work explores the clustering of temperature and relative humidity data, in time series format, as a way to monitor the quality of the information provided by two plant disease alert systems. An approach based on clustering was used to group Florida weather stations according to their microclimate characteristics. The elbow and silhouette methods were used to help find the optimal number of clusters, found to be 3. The K-Means algorithm was used with multivariate time series to group the weather stations. Then, an improvement was proposed to flag suspicious observations and early identify inconsistent measurements, increasing the reliability of the system.
{"title":"Clustering Weather Time Series used for Agricultural Disease Alert Systems in Florida","authors":"M. A. D. Oliveira, G. H. Cavalheiro, Vinícius A. Cerbaro, C. Fraisse","doi":"10.1109/ISORC58943.2023.00029","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00029","url":null,"abstract":"Meteorological observations are widely used as input for disease alert systems in agriculture. In Florida, USA, the AgroClimate Advisory Systems provide disease alerts to growers of various crops, including strawberries, blueberries, and citrus. Data observed in weather stations belonging to FAWN (Florida Automated Weather Network) are used to simulate disease risk, and growers are notified when environmental conditions are favorable for infection, helping them decide when to spray for prevention. However, observation problems in weather stations, such as sensor or communication failures, can compromise the reliability of these applications, which unfortunately are common in this context. Thus, this work explores the clustering of temperature and relative humidity data, in time series format, as a way to monitor the quality of the information provided by two plant disease alert systems. An approach based on clustering was used to group Florida weather stations according to their microclimate characteristics. The elbow and silhouette methods were used to help find the optimal number of clusters, found to be 3. The K-Means algorithm was used with multivariate time series to group the weather stations. Then, an improvement was proposed to flag suspicious observations and early identify inconsistent measurements, increasing the reliability of the system.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124740005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A digital twin (DT) is a virtual replica of a physical system that allows simulation, optimization, and predictive maintenance. Its challenges include the need for accurate and up-to-date data as well as the complexity of integrating different systems and technologies. This paper explores the potential of combining digital twin and blockchain technologies to create next-generation transportation systems that are more efficient, secure, and sustainable. DTs can be used to simulate and optimize transportation operations and maintenance, while blockchain can enhance security and transparency in data exchange and transaction verification. By integrating these technologies, transportation systems can become more resilient, adaptable, and responsive to changing demands and challenges. This paper provides an overview of the key concepts and applications of DTs and blockchain in transportation, including use cases such as autonomous vehicles, smart logistics, and mobility as a service. It also discusses the technical and organizational challenges of implementing these technologies and suggests potential solutions and research directions. Specifically, this paper argues that DT and blockchain technologies have the potential to transform transportation systems into more efficient, sustainable, and equitable systems that can meet the needs of present and future generations.
{"title":"Blockchain-enabled Digital Twin Technology for Next-Generation Transportation Systems","authors":"Sourav Banerjee, Debashis Das, Pushpita Chatterjee, Uttam Ghosh","doi":"10.1109/ISORC58943.2023.00040","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00040","url":null,"abstract":"A digital twin (DT) is a virtual replica of a physical system that allows simulation, optimization, and predictive maintenance. Its challenges include the need for accurate and up-to-date data as well as the complexity of integrating different systems and technologies. This paper explores the potential of combining digital twin and blockchain technologies to create next-generation transportation systems that are more efficient, secure, and sustainable. DTs can be used to simulate and optimize transportation operations and maintenance, while blockchain can enhance security and transparency in data exchange and transaction verification. By integrating these technologies, transportation systems can become more resilient, adaptable, and responsive to changing demands and challenges. This paper provides an overview of the key concepts and applications of DTs and blockchain in transportation, including use cases such as autonomous vehicles, smart logistics, and mobility as a service. It also discusses the technical and organizational challenges of implementing these technologies and suggests potential solutions and research directions. Specifically, this paper argues that DT and blockchain technologies have the potential to transform transportation systems into more efficient, sustainable, and equitable systems that can meet the needs of present and future generations.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125858851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00038
Abhilasha J. Saroj, M. Hunter, Somdut Roy, Angshuman Guin
Development of an arterial smart corridor digital twin requires the integration of real time data streams, data storage, and simulation model execution. This process may be complex, time consuming, and susceptible to errors. To aid in smart corridor digital twin development this paper seeks to provide a framework, best practices, and development guidance. As such, a three-tier incremental approach to smart corridor digital twin development is presented. The paper highlights practical issues in digital twin construction along with key data challenges based on experiences from the development of digital twins for two large Smart Corridor deployments, one in Chattanooga, Tennessee, and the other in Atlanta, Georgia. The presented three-tier incremental approach includes: 1) development of a prepopulated offline simulation, 2) development of a pseudo digital twin that is driven by archived data, and 3) integration of real time data streams to create the online digital twin model. The three-tiered approach facilitates conducting multiple trials and scenarios with increasing complexity, allowing for incremental error processing and updating of the digital twin.
{"title":"A Three-Tier Incremental Approach for Development of Smart Corridor Digital Twins","authors":"Abhilasha J. Saroj, M. Hunter, Somdut Roy, Angshuman Guin","doi":"10.1109/ISORC58943.2023.00038","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00038","url":null,"abstract":"Development of an arterial smart corridor digital twin requires the integration of real time data streams, data storage, and simulation model execution. This process may be complex, time consuming, and susceptible to errors. To aid in smart corridor digital twin development this paper seeks to provide a framework, best practices, and development guidance. As such, a three-tier incremental approach to smart corridor digital twin development is presented. The paper highlights practical issues in digital twin construction along with key data challenges based on experiences from the development of digital twins for two large Smart Corridor deployments, one in Chattanooga, Tennessee, and the other in Atlanta, Georgia. The presented three-tier incremental approach includes: 1) development of a prepopulated offline simulation, 2) development of a pseudo digital twin that is driven by archived data, and 3) integration of real time data streams to create the online digital twin model. The three-tiered approach facilitates conducting multiple trials and scenarios with increasing complexity, allowing for incremental error processing and updating of the digital twin.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126703377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/ISORC58943.2023.00036
Palli Venkata Aishwarya, D. S. Reddy, Dinesh Kumar Sonkar, Poluri Nikhil Koundinya, P. Rajalakshmi
This paper presents a vision-based approach for detecting speed bumps, which is crucial for enabling safe and efficient speed control in autonomous vehicles. Given the diverse range of speed bump sizes and characteristics encountered in Indian scenarios, a robust detection algorithm is required. To this end, we evaluate two state-of-the-art deep learning based object detection models, Faster R-CNN and YOLOv5, and compare their performance. Our study specifically focuses on detecting both marked and unmarked speed bumps in real world environments. However, we also address the challenge of misclassifying pedestrian crosswalks, which can be mistaken for speed bumps due to their similar features. To enhance the accuracy of detecting marked speed bumps, we employ the Negative Sample Training (NST) method. The results show that training with NST improved the detection performance of both Faster R-CNN and YOLOv5 models, achieving an average precision increase of $ 5.58%$ and $ 2.3%$, respectively, for marked speed bump detection. Furthermore, we conduct real-time testing of the proposed model on the NVIDIA Jetson platform, which yields an inference speed of $18.5mathrm{~ms}$ per frame.
{"title":"Robust Deep Learning based Speed Bump Detection for Autonomous Vehicles in Indian Scenarios","authors":"Palli Venkata Aishwarya, D. S. Reddy, Dinesh Kumar Sonkar, Poluri Nikhil Koundinya, P. Rajalakshmi","doi":"10.1109/ISORC58943.2023.00036","DOIUrl":"https://doi.org/10.1109/ISORC58943.2023.00036","url":null,"abstract":"This paper presents a vision-based approach for detecting speed bumps, which is crucial for enabling safe and efficient speed control in autonomous vehicles. Given the diverse range of speed bump sizes and characteristics encountered in Indian scenarios, a robust detection algorithm is required. To this end, we evaluate two state-of-the-art deep learning based object detection models, Faster R-CNN and YOLOv5, and compare their performance. Our study specifically focuses on detecting both marked and unmarked speed bumps in real world environments. However, we also address the challenge of misclassifying pedestrian crosswalks, which can be mistaken for speed bumps due to their similar features. To enhance the accuracy of detecting marked speed bumps, we employ the Negative Sample Training (NST) method. The results show that training with NST improved the detection performance of both Faster R-CNN and YOLOv5 models, achieving an average precision increase of $ 5.58%$ and $ 2.3%$, respectively, for marked speed bump detection. Furthermore, we conduct real-time testing of the proposed model on the NVIDIA Jetson platform, which yields an inference speed of $18.5mathrm{~ms}$ per frame.","PeriodicalId":281426,"journal":{"name":"2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131450269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：